{"id":"https://openalex.org/W4412887020","doi":"https://doi.org/10.18653/v1/2025.acl-long.11","title":"StrucText-Eval: Evaluating Large Language Model\u2019s Reasoning Ability in Structure-Rich Text","display_name":"StrucText-Eval: Evaluating Large Language Model\u2019s Reasoning Ability in Structure-Rich Text","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887020","doi":"https://doi.org/10.18653/v1/2025.acl-long.11"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.11","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.11","pdf_url":"https://aclanthology.org/2025.acl-long.11.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.11.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089987379","display_name":"Zhouhong Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhouhong Gu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003011911","display_name":"Haoning Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoning Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039782834","display_name":"Xingzhou Chen","orcid":"https://orcid.org/0000-0003-1631-5202"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingzhou Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016573862","display_name":"Zeyang Zhou","orcid":"https://orcid.org/0000-0003-2296-0742"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeyang Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101918960","display_name":"Hongwei Feng","orcid":"https://orcid.org/0009-0005-6004-726X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongwei Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090455375","display_name":"Yanghua Xiao","orcid":"https://orcid.org/0000-0001-8403-9591"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanghua Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"223","last_page":"244"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9656000137329102,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9656000137329102,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9650999903678894,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7386931777000427},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6597522497177124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49907541275024414},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4448612630367279},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3214036524295807}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7386931777000427},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6597522497177124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49907541275024414},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4448612630367279},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3214036524295807},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.11","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.11","pdf_url":"https://aclanthology.org/2025.acl-long.11.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.11","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.11","pdf_url":"https://aclanthology.org/2025.acl-long.11.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5877446384","display_name":null,"funder_award_id":"62476145","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887020.pdf","grobid_xml":"https://content.openalex.org/works/W4412887020.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"effective":[1],"utilization":[2],"of":[3,17,23,141,163],"structured":[4,34,62,98],"data,":[5],"integral":[6],"to":[7,56,89,151],"corporate":[8],"data":[9,35,45,68],"strategies,":[10],"has":[11],"been":[12],"challenged":[13],"by":[14],"the":[15,29,117,120,144,154],"rise":[16],"large":[18],"language":[19],"models":[20],"(LLMs)":[21],"capable":[22],"processing":[24],"unstructured":[25,39],"information.This":[26],"shift":[27],"prompts":[28],"question:":[30],"can":[31],"LLMs":[32,93,136],"interpret":[33],"directly":[36],"in":[37,171,183],"its":[38],"form?We":[40],"propose":[41],"an":[42,161],"automatic":[43],"evaluation":[44],"generation":[46,178],"method":[47],"for":[48],"assessing":[49],"LLMs'":[50,168],"reasoning":[51],"capabilities":[52],"on":[53,127,143,153,165],"structurerich":[54],"text":[55],"explore":[57],"this.Our":[58],"approach":[59],"supports":[60],"8":[61],"languages":[63],"and":[64,75,85,95,111,124,177],"29":[65],"tasks,":[66],"generating":[67],"with":[69],"adjustable":[70],"complexity":[71],"through":[72,97],"controllable":[73],"nesting":[74],"structural":[76,174],"width.We":[77],"introduce":[78],"StrucText-Eval,":[79],"a":[80,105,112,138],"benchmark":[81,176],"containing":[82],"5,800":[83],"pre-generated":[84],"annotated":[86],"samples":[87],"designed":[88],"evaluate":[90],"how":[91],"well":[92],"understand":[94],"reason":[96],"text.StrucText-Eval":[99],"is":[100],"divided":[101],"into":[102],"two":[103],"suites:":[104],"regular":[106],"Test":[107],"suite":[108,114],"(3,712":[109],"samples)":[110],"Test-Hard":[113],"(2,088":[115],"samples),":[116],"latter":[118],"emphasizing":[119],"gap":[121],"between":[122],"human":[123,158],"model":[125],"performance":[126,148],"more":[128],"complex":[129],"tasks.Experimental":[130],"results":[131],"show":[132],"that":[133],"while":[134],"open-source":[135],"achieve":[137],"maximum":[139],"accuracy":[140,162],"74.9%":[142],"standard":[145],"dataset,":[146],"their":[147],"drops":[149],"significantly":[150],"45.8%":[152],"harder":[155],"dataset.In":[156],"contrast,":[157],"participants":[159],"reach":[160],"92.6%":[164],"StrucText-Eval-Hard,":[166],"highlighting":[167],"current":[169],"limitations":[170],"handling":[172],"intricate":[173],"information.The":[175],"codes":[179],"are":[180],"open":[181],"sourced":[182],"https://github.com/MikeGu721/":[184],"StrucText-Eval":[185]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}